Handheld visual inspection device and pose detection method thereof

Abstract

The present invention discloses a handheld visual inspection device and a pose detection method thereof, the device comprising a laser, a vision acquisition element, a control and data processing module, and an output module. The laser is used for projecting laser to the surface of an object to be inspected. The vision acquisition element is used for acquiring an image. The control and data processing module performs the following on the image: (1) preprocessing the image and extracting a light bar / center point of a light spot; (2) with a horizontal / longitudinal edge of the image as a baseline, taking the line formed by the light bar / center point of the light spot as the line to be inspected, calculating the included angle gamma between the two and judging whether the included angle is within a preset scope; (3) determining the position of the center point of the line to be inspected, calculating distance d thereof to a upper side edge / a lower side edge, and surveying whether the distance d is within a preset value scope; and displaying an inspection result. The technical solution can display a relative position relationship between the inspection device and the object to be inspected on a real time basis and facilitate an operator for timely adjusting the angle and distance, thereby improving inspection precision and stability of the device.

Description

technical field [0001] The invention relates to the field of machine vision detection, in particular to a hand-held visual detection device and a pose detection method thereof. Background technique [0002] In visual measurement technology, the visual acquisition components in the detection equipment are often fixed inside the equipment. The quality of the acquired image depends on the positional relationship between the inspection equipment and the measured object, especially the hand-held inspection equipment. If the relative position of the detection equipment and the measured object has a large inclination angle, there may be a blind area of ​​image acquisition, so that the characteristic target of the measured object is not in the detection area; and when the distance between the detection equipment and the measured object is too far or too close, Especially when the characteristic target of the measured object is not within the depth of field of the detection equipmen...

AI Technical Summary

Problems solved by technology

The first) method encounters arc and other test scenarios, and the mechanical structure of the limit function fails; the second) method has high requirements on the equipment hardware and takes a long time to calculate, which is not suitable for real-time detection, and cannot detect the equipment and the target angle between

Images